A query based graph-oriented load-shedding for RDF stream processing

To cope with heterogeneity of data in streams, Semantic Web technologies (RDFVSPARQL2) have recently been used for annotation, publication and reasoning on these data. To deal with this new kind of streams, researchers have proposed new systems named RDF Stream Processing (RSP). Unfortunately, in limited system resources environment, these systems are fallible as soon as their maximum supported speed is reached. To overcome these problems, some efforts have been done in this area. Most of them, based on a triple-oriented approach and according to a probabilistic method, decrease the volume of RDF data stream using load-shedding techniques. In this paper we propose an enhancement of a Graph-Oriented approach for load-shedding semantic data streams, by considering the continuous query as input. Conducted experiments show that we can keep the RSP's recall at 100% even if we drop more than half of data.